增加新源，过滤简介中的特殊字符，提高爬虫兼容性

README.md

@@ -1,7 +1,15 @@
-[![index](./assets/热门云产品1040.100.jpg)](https://cloud.tencent.com/act/cps/redirect?redirect=1052&cps_key=736e609d66e0ac4e57813316cec6fd0b&from=console)
+[![index]( https://i.loli.net/2020/06/01/qF1uBMtswTIPJKx.jpg )]( https://www.eve.bz/cart.php?gid=11 )
 
 # 小说精品屋-plus
 
+#### 新项目：小说精品屋-微服务版
+
+基于小说精品屋-plus构建的Spring Cloud 微服务小说门户平台，可用于学习和商用。
+
+Gitee仓库地址： https://gitee.com/xiongxyang/novel-cloud
+
+GitHub仓库地址： https://github.com/201206030/novel-cloud
+
 #### 演示地址
 
 [点击前往](http://www.java2nb.com)（前台门户）
@@ -48,6 +56,7 @@ novel-plus -- 父工程
 | MyBatis Dynamic SQL  | Mybatis动态sql
 | PageHelper           | MyBatis分页插件
 | MyBatisGenerator     | 持久层代码生成插件
+| Sharding-Jdbc        | 代码层分库分表中间件
 | JJWT                 | JWT登录支持  
 | SpringSecurity       | 安全框架                           
 | Shiro                | 安全框架  

novel-common/pom.xml

@@ -5,7 +5,7 @@
     <parent>
         <artifactId>novel</artifactId>
         <groupId>com.java2nb</groupId>
-        <version>2.1.2</version>
+        <version>2.5.1</version>
     </parent>
     <modelVersion>4.0.0</modelVersion>
 
@@ -57,6 +57,22 @@
             <version>${mybatis.version}</version>
         </dependency>
 
+        <!-- 分库分表-->
+        <!-- sharding jdbc依赖 -->
+
+        <dependency>
+            <groupId>io.shardingsphere</groupId>
+            <artifactId>sharding-jdbc-spring-boot-starter</artifactId>
+            <version>${sharding.jdbc.version}</version>
+        </dependency>
+
+        <dependency>
+            <groupId>io.shardingsphere</groupId>
+            <artifactId>sharding-jdbc-spring-namespace</artifactId>
+            <version>${sharding.jdbc.version}</version>
+        </dependency>
+
+
         <!--分页助手启动器-->
         <dependency>
             <groupId>com.github.pagehelper</groupId>

novel-common/src/main/java/com/java2nb/novel/mapper/BookContentDynamicSqlSupport.java

@@ -24,7 +24,7 @@ public final class BookContentDynamicSqlSupport {
 
         public final SqlColumn<Long> indexId = column("index_id", JDBCType.BIGINT);
 
-        public final SqlColumn<String> content = column("content", JDBCType.LONGVARCHAR);
+        public final SqlColumn<String> content = column("content", JDBCType.VARCHAR);
 
         public BookContent() {
             super("book_content");

novel-common/src/main/java/com/java2nb/novel/mapper/BookContentMapper.java

@@ -63,7 +63,7 @@ public interface BookContentMapper {
     @Results(id="BookContentResult", value = {
         @Result(column="id", property="id", jdbcType=JdbcType.BIGINT, id=true),
         @Result(column="index_id", property="indexId", jdbcType=JdbcType.BIGINT),
-        @Result(column="content", property="content", jdbcType=JdbcType.LONGVARCHAR)
+        @Result(column="content", property="content", jdbcType=JdbcType.VARCHAR)
     })
     List<BookContent> selectMany(SelectStatementProvider selectStatement);
 

novel-common/src/main/resources/application-common-dev.yml

@@ -1,11 +1,8 @@
 spring:
   profiles:
     include: [common]
-  datasource:
-    url: jdbc:mysql://127.0.0.1:3306/novel_plus?useUnicode=true&characterEncoding=utf-8&useSSL=false&serverTimezone=Asia/Shanghai
-    username: root
-    password: test123456
-    driver-class-name: com.mysql.cj.jdbc.Driver
+  main:
+    allow-bean-definition-overriding: true
   #Redis服务器IP
   redis:
     host: 127.0.0.1
@@ -25,6 +22,51 @@ spring:
         min-idle: 0
     #连接超时时间（毫秒）
     timeout: 30000
+  datasource:
+    url: jdbc:mysql://127.0.0.1:3306/novel_plus?useUnicode=true&characterEncoding=utf-8&useSSL=false&serverTimezone=Asia/Shanghai
+    username: root
+    password: test123456
+    driver-class-name: com.mysql.cj.jdbc.Driver
+
+####使用shardingJdbc时，
+####所有的jdbcType都不能是LONGVARCHAR,否则会导致java.io.NotSerializableException: java.io.StringReader错误
+##### 应该替换所有的 LONGVARCHAR 类型为VARCHAR
+
+sharding:
+  jdbc:
+    datasource:
+      names: ds0 #,ds1
+      ds0:
+        type: com.zaxxer.hikari.HikariDataSource
+        driver-class-name: com.mysql.cj.jdbc.Driver
+        jdbc-url: jdbc:mysql://localhost:3306/novel_plus?useUnicode=true&characterEncoding=utf-8&useSSL=false&serverTimezone=Asia/Shanghai
+        username: root
+        password: test123456
+#      ds1:
+#        type: com.alibaba.druid.pool.DruidDataSource
+#        driver-class-name: com.mysql.jdbc.Driver
+#        url: jdbc:mysql://localhost:3306/novel_plus2
+#        username: root
+#        password: test123456
+    config:
+      sharding:
+        props:
+          sql.show: true
+        tables:
+          book_content:  #book_content表
+            key-generator-column-name: id  #主键
+            actual-data-nodes: ds${0}.book_content${0..9}  #数据节点
+#            database-strategy:  #分库策略
+#              inline:
+#                sharding-column: book_id
+#                algorithm-expression: ds${book_id % 10}
+            table-strategy:  #分表策略
+              inline:
+                shardingColumn: index_id
+                algorithm-expression: book_content${index_id % 10}
+
+
+
 
 
 

novel-crawl/pom.xml

@@ -5,7 +5,7 @@
     <parent>
         <artifactId>novel</artifactId>
         <groupId>com.java2nb</groupId>
-        <version>2.1.2</version>
+        <version>2.5.1</version>
     </parent>
     <modelVersion>4.0.0</modelVersion>
 
@@ -25,6 +25,8 @@
             <groupId>org.springframework.boot</groupId>
             <artifactId>spring-boot-starter-security</artifactId>
         </dependency>
+
+
     </dependencies>
 
     <build>

novel-crawl/src/main/java/com/java2nb/novel/core/crawl/CrawlParser.java

@@ -96,8 +96,12 @@ public class CrawlParser {
 
                     String desc = bookDetailHtml.substring(bookDetailHtml.indexOf(ruleBean.getDescStart()) + ruleBean.getDescStart().length());
                     desc = desc.substring(0, desc.indexOf(ruleBean.getDescEnd()));
-                    //过滤掉简介中的a标签
-                    desc = desc.replaceAll("<a[^<]+</a>","");
+                    //过滤掉简介中的特殊标签
+                    desc = desc.replaceAll("<a[^<]+</a>","")
+                            .replaceAll("<font[^<]+</font>","")
+                            .replaceAll("<p>\\s*</p>","")
+                            .replaceAll("<p>","")
+                            .replaceAll("</p>","<br/>");
                     //设置书籍简介
                     book.setBookDesc(desc);
                     if (StringUtils.isNotBlank(ruleBean.getStatusPatten())) {

novel-front/pom.xml

@@ -5,7 +5,7 @@
     <parent>
         <artifactId>novel</artifactId>
         <groupId>com.java2nb</groupId>
-        <version>2.1.2</version>
+        <version>2.5.1</version>
     </parent>
     <modelVersion>4.0.0</modelVersion>
 
@@ -43,24 +43,19 @@
         <dependency>
             <groupId>com.aliyun.oss</groupId>
             <artifactId>aliyun-sdk-oss</artifactId>
-            <version>2.4.0</version>
+            <version>${aliyun-sdk-oss.version}</version>
         </dependency>
         <dependency>
             <groupId>commons-fileupload</groupId>
             <artifactId>commons-fileupload</artifactId>
-            <version>1.3.1</version>
+            <version>${commons-fileupload.version}</version>
         </dependency>
 
         <!--FastDfs-->
-        <dependency>
-            <groupId>org.springframework</groupId>
-            <artifactId>spring-mock</artifactId>
-            <version>2.0.8</version>
-        </dependency>
         <dependency>
             <groupId>com.github.tobato</groupId>
             <artifactId>fastdfs-client</artifactId>
-            <version>1.26.1-RELEASE</version>
+            <version>${fastdfs-client.version}</version>
         </dependency>
 
         <dependency>
@@ -69,6 +64,8 @@
         </dependency>
 
 
+
+
         <!--引入redisson分布式锁-->
        <!-- <dependency>
             <groupId>org.redisson</groupId>
@@ -80,7 +77,7 @@
         <dependency>
             <groupId>com.alipay.sdk</groupId>
             <artifactId>alipay-sdk-java</artifactId>
-            <version>4.9.153.ALL</version>
+            <version>${alipay-sdk-java.version}</version>
         </dependency>
     </dependencies>
 

novel-front/src/main/java/com/java2nb/novel/FrontNovelApplication.java

@@ -1,6 +1,7 @@
 package com.java2nb.novel;
 
 import com.github.tobato.fastdfs.FdfsClientConfig;
+import io.shardingsphere.shardingjdbc.spring.boot.SpringBootConfiguration;
 import org.mybatis.spring.annotation.MapperScan;
 import org.springframework.boot.SpringApplication;
 import org.springframework.boot.autoconfigure.SpringBootApplication;

pom.xml

@@ -5,7 +5,7 @@
 
     <groupId>com.java2nb</groupId>
     <artifactId>novel</artifactId>
-    <version>2.1.2</version>
+    <version>2.5.1</version>
     <modules>
         <module>novel-common</module>
         <module>novel-front</module>
@@ -40,6 +40,11 @@
         <jest.version>6.3.1</jest.version>
         <redis.version>1.4.1.RELEASE</redis.version>
         <redisson.version>3.12.5</redisson.version>
+        <sharding.jdbc.version>3.0.0</sharding.jdbc.version>
+        <aliyun-sdk-oss.version>2.4.0</aliyun-sdk-oss.version>
+        <commons-fileupload.version>1.3.1</commons-fileupload.version>
+        <fastdfs-client.version>1.26.1-RELEASE</fastdfs-client.version>
+        <alipay-sdk-java.version>4.9.153.ALL</alipay-sdk-java.version>
     </properties>
 
     <dependencyManagement>

sql/20200608.sql

@@ -0,0 +1,2 @@
+INSERT INTO `crawl_source` (`id`, `source_name`, `crawl_rule`, `source_status`, `create_time`, `update_time`) VALUES
+(6, '新笔趣阁', '{\n	\"bookListUrl\": \"http://www.xbiquge.la/fenlei/{catId}_{page}.html\",\n	\"catIdRule\": {\n		\"catId1\": \"1\",\n		\"catId2\": \"2\",\n		\"catId3\": \"3\",\n		\"catId4\": \"4\",\n		\"catId5\": \"6\",\n		\"catId6\": \"5\"\n	},\n	\"bookIdPatten\": \"<a\\\\s+href=\\\"http://www.xbiquge.la/(\\\\d+/\\\\d+)/\\\"\\\\s+target=\\\"_blank\\\">\",\n	\"pagePatten\": \"<em\\\\s+id=\\\"pagestats\\\">(\\\\d+)/\\\\d+</em>\",\n	\"totalPagePatten\": \"<em\\\\s+id=\\\"pagestats\\\">\\\\d+/(\\\\d+)</em>\",\n	\"bookDetailUrl\": \"http://www.xbiquge.la/{bookId}/\",\n	\"bookNamePatten\": \"<h1>([^/]+)</h1>\",\n	\"authorNamePatten\": \"者：([^/]+)</p>\",\n	\"picUrlPatten\": \"src=\\\"(http://www.xbiquge.la/files/article/image/\\\\d+/\\\\d+/\\\\d+s\\\\.jpg)\\\"\",\n	\"bookStatusRule\": {},\n	\"descStart\": \"<div id=\\\"intro\\\">\",\n	\"descEnd\": \"</div>\",\n	\"upadateTimePatten\": \"<p>最后更新：(\\\\d+-\\\\d+-\\\\d+\\\\s\\\\d+:\\\\d+:\\\\d+)</p>\",\n	\"upadateTimeFormatPatten\": \"yyyy-MM-dd HH:mm:ss\",\n	\"bookIndexUrl\": \"http://www.xbiquge.la/{bookId}/\",\n	\"indexIdPatten\": \"<a\\\\s+href=\'/\\\\d+/\\\\d+/(\\\\d+)\\\\.html\'\\\\s+>[^/]+</a>\",\n	\"indexNamePatten\": \"<a\\\\s+href=\'/\\\\d+/\\\\d+/\\\\d+\\\\.html\'\\\\s+>([^/]+)</a>\",\n	\"bookContentUrl\": \"http://www.xbiquge.la/{bookId}/{indexId}.html\",\n	\"contentStart\": \"<div id=\\\"content\\\">\",\n	\"contentEnd\": \"<p>\"\n}', 0, '2020-05-23 22:46:58', '2020-05-23 22:46:58');

sql/novel_plus.sql

@@ -1691,4 +1691,122 @@ INSERT INTO `user_read_history` VALUES ('113', '1255060328322027520', '125467697
 INSERT INTO `user_read_history` VALUES ('117', '1255060328322027520', '1254946661743603712', '1254946914001629184', '2020-04-30 19:37:09', '2020-04-30 19:37:09');
 INSERT INTO `user_read_history` VALUES ('118', '1255060328322027520', '1254957312633352192', '3335449', '2020-04-30 19:37:36', '2020-04-30 19:37:36');
 
+
+
+DROP TABLE IF EXISTS `book_content0`;
+CREATE TABLE `book_content0` (
+  `id` bigint(20) NOT NULL AUTO_INCREMENT COMMENT '主键',
+  `index_id` bigint(20) DEFAULT NULL COMMENT '目录ID',
+  `content` mediumtext COMMENT '小说章节内容',
+  PRIMARY KEY (`id`),
+  UNIQUE KEY `key_uq_indexId` (`index_id`) USING BTREE
+) ENGINE=InnoDB AUTO_INCREMENT=1155 DEFAULT CHARSET=utf8mb4 COMMENT='小说内容表';
+
+-- ----------------------------
+-- Table structure for book_content1
+-- ----------------------------
+DROP TABLE IF EXISTS `book_content1`;
+CREATE TABLE `book_content1` (
+  `id` bigint(20) NOT NULL AUTO_INCREMENT COMMENT '主键',
+  `index_id` bigint(20) DEFAULT NULL COMMENT '目录ID',
+  `content` mediumtext COMMENT '小说章节内容',
+  PRIMARY KEY (`id`),
+  UNIQUE KEY `key_uq_indexId` (`index_id`) USING BTREE
+) ENGINE=InnoDB AUTO_INCREMENT=406 DEFAULT CHARSET=utf8mb4 COMMENT='小说内容表';
+
+-- ----------------------------
+-- Table structure for book_content2
+-- ----------------------------
+DROP TABLE IF EXISTS `book_content2`;
+CREATE TABLE `book_content2` (
+  `id` bigint(20) NOT NULL AUTO_INCREMENT COMMENT '主键',
+  `index_id` bigint(20) DEFAULT NULL COMMENT '目录ID',
+  `content` mediumtext COMMENT '小说章节内容',
+  PRIMARY KEY (`id`),
+  UNIQUE KEY `key_uq_indexId` (`index_id`) USING BTREE
+) ENGINE=InnoDB AUTO_INCREMENT=1222 DEFAULT CHARSET=utf8mb4 COMMENT='小说内容表';
+
+-- ----------------------------
+-- Table structure for book_content3
+-- ----------------------------
+DROP TABLE IF EXISTS `book_content3`;
+CREATE TABLE `book_content3` (
+  `id` bigint(20) NOT NULL AUTO_INCREMENT COMMENT '主键',
+  `index_id` bigint(20) DEFAULT NULL COMMENT '目录ID',
+  `content` mediumtext COMMENT '小说章节内容',
+  PRIMARY KEY (`id`),
+  UNIQUE KEY `key_uq_indexId` (`index_id`) USING BTREE
+) ENGINE=InnoDB AUTO_INCREMENT=410 DEFAULT CHARSET=utf8mb4 COMMENT='小说内容表';
+
+-- ----------------------------
+-- Table structure for book_content4
+-- ----------------------------
+DROP TABLE IF EXISTS `book_content4`;
+CREATE TABLE `book_content4` (
+  `id` bigint(20) NOT NULL AUTO_INCREMENT COMMENT '主键',
+  `index_id` bigint(20) DEFAULT NULL COMMENT '目录ID',
+  `content` mediumtext COMMENT '小说章节内容',
+  PRIMARY KEY (`id`),
+  UNIQUE KEY `key_uq_indexId` (`index_id`) USING BTREE
+) ENGINE=InnoDB AUTO_INCREMENT=1188 DEFAULT CHARSET=utf8mb4 COMMENT='小说内容表';
+
+-- ----------------------------
+-- Table structure for book_content5
+-- ----------------------------
+DROP TABLE IF EXISTS `book_content5`;
+CREATE TABLE `book_content5` (
+  `id` bigint(20) NOT NULL AUTO_INCREMENT COMMENT '主键',
+  `index_id` bigint(20) DEFAULT NULL COMMENT '目录ID',
+  `content` mediumtext COMMENT '小说章节内容',
+  PRIMARY KEY (`id`),
+  UNIQUE KEY `key_uq_indexId` (`index_id`) USING BTREE
+) ENGINE=InnoDB AUTO_INCREMENT=416 DEFAULT CHARSET=utf8mb4 COMMENT='小说内容表';
+
+-- ----------------------------
+-- Table structure for book_content6
+-- ----------------------------
+DROP TABLE IF EXISTS `book_content6`;
+CREATE TABLE `book_content6` (
+  `id` bigint(20) NOT NULL AUTO_INCREMENT COMMENT '主键',
+  `index_id` bigint(20) DEFAULT NULL COMMENT '目录ID',
+  `content` mediumtext COMMENT '小说章节内容',
+  PRIMARY KEY (`id`),
+  UNIQUE KEY `key_uq_indexId` (`index_id`) USING BTREE
+) ENGINE=InnoDB AUTO_INCREMENT=1180 DEFAULT CHARSET=utf8mb4 COMMENT='小说内容表';
+
+-- ----------------------------
+-- Table structure for book_content7
+-- ----------------------------
+DROP TABLE IF EXISTS `book_content7`;
+CREATE TABLE `book_content7` (
+  `id` bigint(20) NOT NULL AUTO_INCREMENT COMMENT '主键',
+  `index_id` bigint(20) DEFAULT NULL COMMENT '目录ID',
+  `content` mediumtext COMMENT '小说章节内容',
+  PRIMARY KEY (`id`),
+  UNIQUE KEY `key_uq_indexId` (`index_id`) USING BTREE
+) ENGINE=InnoDB AUTO_INCREMENT=404 DEFAULT CHARSET=utf8mb4 COMMENT='小说内容表';
+
+-- ----------------------------
+-- Table structure for book_content8
+-- ----------------------------
+DROP TABLE IF EXISTS `book_content8`;
+CREATE TABLE `book_content8` (
+  `id` bigint(20) NOT NULL AUTO_INCREMENT COMMENT '主键',
+  `index_id` bigint(20) DEFAULT NULL COMMENT '目录ID',
+  `content` mediumtext COMMENT '小说章节内容',
+  PRIMARY KEY (`id`),
+  UNIQUE KEY `key_uq_indexId` (`index_id`) USING BTREE
+) ENGINE=InnoDB AUTO_INCREMENT=1134 DEFAULT CHARSET=utf8mb4 COMMENT='小说内容表';
+
+-- ----------------------------
+-- Table structure for book_content9
+-- ----------------------------
+DROP TABLE IF EXISTS `book_content9`;
+CREATE TABLE `book_content9` (
+  `id` bigint(20) NOT NULL AUTO_INCREMENT COMMENT '主键',
+  `index_id` bigint(20) DEFAULT NULL COMMENT '目录ID',
+  `content` mediumtext COMMENT '小说章节内容',
+  PRIMARY KEY (`id`),
+  UNIQUE KEY `key_uq_indexId` (`index_id`) USING BTREE
+) ENGINE=InnoDB AUTO_INCREMENT=415 DEFAULT CHARSET=utf8mb4 COMMENT='小说内容表';
 UPDATE `crawl_source` SET `source_name` = '书趣阁', `crawl_rule` = '{\n	\"bookListUrl\": \"http://m.shuquge.com/sort/{catId}/0_{page}.html\",\n	\"catIdRule\": {\n		\"catId1\": \"1\",\n		\"catId2\": \"2\",\n		\"catId3\": \"3\",\n		\"catId4\": \"4\",\n		\"catId5\": \"7\",\n		\"catId6\": \"6\",\n		\"catId7\": \"8\"\n	},\n	\"bookIdPatten\": \"href=\\\"/s/(\\\\d+)\\\\.html\\\"\",\n	\"pagePatten\": \"第(\\\\d+)/\\\\d+页\",\n	\"totalPagePatten\": \"第\\\\d+/(\\\\d+)页\",\n	\"bookDetailUrl\": \"http://m.shuquge.com/s/{bookId}.html\",\n	\"bookNamePatten\": \"<a\\\\s+href=\\\"/s/\\\\d+\\\\.html\\\"><h2>([^/]+)</h2></a>\",\n	\"authorNamePatten\": \"<p>作者：([^/]+)</p>\",\n	\"picUrlPatten\": \"src=\\\"(http://www.shuquge.com/files/article/image/\\\\d+/\\\\d+/\\\\d+s\\\\.jpg)\\\"\",\n	\"statusPatten\": \"<p>状态：([^/]+)</p>\",\n	\"bookStatusRule\": {\n		\"连载中\": 0,\n		\"完本\": 1\n	},\n	\"descStart\": \"<div class=\\\"intro_info\\\">\",\n	\"descEnd\": \"最新章节推荐地址\",\n	\"bookIndexUrl\": \"http://www.shuquge.com/txt/{bookId}/index.html\",\n	\"bookIndexStart\": \"<dt>《\",\n	\"indexIdPatten\": \"<dd><a\\\\s+href=\\\"(\\\\d+)\\\\.html\\\">[^/]+</a></dd>\",\n	\"indexNamePatten\": \"<dd><a\\\\s+href=\\\"\\\\d+\\\\.html\\\">([^/]+)</a></dd>\",\n	\"bookContentUrl\": \"http://www.shuquge.com/txt/{bookId}/{indexId}.html\",\n	\"contentStart\": \"<div id=\\\"content\\\" class=\\\"showtxt\\\">\",\n	\"contentEnd\": \"http://www.shuquge.com\"\n}', `source_status` = 1, `create_time` = '2020-05-18 12:02:34', `update_time` = '2020-05-18 12:02:34' WHERE `id` = 4;